Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating impossibility or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating impossibility or lack of options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asts
    -0.85
    eg
    -0.80
    ilts
    -0.75
    aples
    -0.74
     livest
    -0.73
    rongh
    -0.72
    etheus
    -0.69
    eals
    -0.67
    ines
    -0.65
    inem
    -0.64
    POSITIVE LOGITS
     whatsoever
    0.94
     anymore
    0.80
     else
    0.73
     anybody
    0.71
    point
    0.68
    fy
    0.67
     THEY
    0.67
     anyone
    0.66
     bothered
    0.62
    Reviewer
    0.61
    Act Density 0.042%

    No Known Activations